detrex: Benchmarking Detection Transformers
This provides a standardized platform for researchers to evaluate and compare DETR-based models, fostering advancements in instance recognition, though it is incremental as it builds on existing DETR methods.
The authors tackled the lack of a unified benchmark for DETR-based models by developing detrex, a modular codebase that supports mainstream DETR algorithms for tasks like object detection and segmentation, and they enhanced performance through hyper-parameter refinement, providing strong baselines.
The DEtection TRansformer (DETR) algorithm has received considerable attention in the research community and is gradually emerging as a mainstream approach for object detection and other perception tasks. However, the current field lacks a unified and comprehensive benchmark specifically tailored for DETR-based models. To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation. We conduct extensive experiments under detrex and perform a comprehensive benchmark for DETR-based models. Moreover, we enhance the performance of detection transformers through the refinement of training hyper-parameters, providing strong baselines for supported algorithms.We hope that detrex could offer research communities a standardized and unified platform to evaluate and compare different DETR-based models while fostering a deeper understanding and driving advancements in DETR-based instance recognition. Our code is available at https://github.com/IDEA-Research/detrex. The project is currently being actively developed. We encourage the community to use detrex codebase for further development and contributions.